Sciweavers

2924 search results - page 231 / 585
» On the Use of Evidence in Neural Networks
Sort
View
ESANN
2003
15 years 8 months ago
Autonomous learning algorithm for fully connected recurrent networks
In this paper fully connected RTRL neural networks are studied. In order to learn dynamical behaviours of linear-processes or to predict time series, an autonomous learning algori...
Edouard Leclercq, Fabrice Druaux, Dimitri Lefebvre
ICANN
2007
Springer
15 years 10 months ago
The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences
We present an artificial neural network used to learn online complex temporal sequences of gestures to a robot. The system is based on a simple temporal sequences learning architec...
Matthieu Lagarde, Pierre Andry, Philippe Gaussier
ESANN
2001
15 years 8 months ago
Input data reduction for the prediction of financial time series
Prediction of financial time series using artificial neural networks has been the subject of many publications, even if the predictability of financial series remains a subject of ...
Amaury Lendasse, John Aldo Lee, Eric de Bodt, Vinc...
ICASSP
2011
IEEE
14 years 10 months ago
Deep belief nets for natural language call-routing
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...
IFGIS
2009
Springer
16 years 1 months ago
Application of Self-Organizing Maps to the Maritime Environment
Self-Organizing Maps (SOMs), or Kohonen networks, are widely used neural network architecture. This paper starts with a brief overview of how SOMs can be used in different types of...
Victor Sousa Lobo